CVE-2026-48746 vLLM: OpenAI auth bypass

What is CVE-2026-48746?

CVE-2026-48746 is a critical authentication bypass vulnerability in Vllm Vllm, published on 22 Jun 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.

Weakness: CWE-501, CWE-444

Which versions are affected by CVE-2026-48746?

3 open source packages ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-48746?

Upgrade vllm to 0.22.0 or later.

Upgrade, and rotate credentials and sessions that may have been exposed. More about Authentication bypass.

Is CVE-2026-48746 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-48746 exists.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2025-29783 vLLM Allows Remote Code Execution via Mooncake Integration Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-94f4-hr76-p5j6, MINI-357x-mh56-h27j, MINI-9g3f-jm52-5vcc, MINI-fvcq-7xm6-xvx9, PYSEC-2026-226.